Commit Graph

56 Commits

Author SHA1 Message Date
Xyfacai
c674c3561a fix(response): tools 需要处理的参数很少 使用 map 2025-07-20 11:21:57 +08:00
t0ng7u
93b5638a9c Merge remote-tracking branch 'origin/multi_keys_channel' into alpha
# Conflicts:
#	web/src/components/table/LogsTable.js
#	web/src/i18n/locales/en.json
#	web/src/pages/Channel/EditChannel.js
2025-07-12 23:47:24 +08:00
RedwindA
22a0ed0ee2 feat: 支持 xAI 网络搜索 2025-07-12 02:22:40 +08:00
CaIon
98952198bb refactor: Introduce standardized API error
This commit refactors the application's error handling mechanism by introducing a new standardized error type, `types.NewAPIError`. It also renames common JSON utility functions for better clarity.

Previously, internal error handling was tightly coupled to the `dto.OpenAIError` format. This change decouples the internal logic from the external API representation.

Key changes:
- A new `types.NewAPIError` struct is introduced to serve as a canonical internal representation for all API errors.
- All relay adapters (OpenAI, Claude, Gemini, etc.) are updated to return `*types.NewAPIError`.
- Controllers now convert the internal `NewAPIError` to the client-facing `OpenAIError` format at the API boundary, ensuring backward compatibility.
- Channel auto-disable/enable logic is updated to use the new standardized error type.
- JSON utility functions are renamed to align with Go's standard library conventions (e.g., `UnmarshalJson` -> `Unmarshal`, `EncodeJson` -> `Marshal`).
2025-07-10 15:02:40 +08:00
CaIon
6b9237f868 🐛 fix: refactor JSON unmarshalling across multiple handlers to use UnmarshalJson and UnmarshalJsonStr for consistency
This update replaces instances of DecodeJson and DecodeJsonStr with UnmarshalJson and UnmarshalJsonStr in various relay handlers, enhancing code consistency and clarity in JSON processing. The changes improve maintainability and align with recent refactoring efforts in the codebase.
2025-06-28 00:02:07 +08:00
CaIon
1dad04ec09 feat: add Function and Container fields to ResponsesToolsCall struct #1305 2025-06-27 16:56:54 +08:00
Calcium-Ion
fd4447f60a Merge pull request #1120 from neotf/feat-04
feat: enhance token usage details for upstream OpenRouter
2025-06-22 01:10:49 +08:00
KamiPasi
d5a3eb7d04 透传thinking参数, 豆包模型用来控制是否思考 2025-06-19 12:06:42 +08:00
neotf
81bc096872 Merge branch 'main' into feat-04 2025-06-18 15:20:24 +08:00
CaIon
be7e09b14d feat(dto): add VlHighResolutionImages parameter to GeneralOpenAIRequest 2025-06-13 17:29:26 +08:00
neotf
d67d5d8006 format 2025-06-11 14:00:32 +08:00
neotf
c4f25a77d1 format 2025-06-11 13:56:44 +08:00
neotf
52763c09f2 Merge branch 'main' into feat-04 2025-06-11 13:55:47 +08:00
Calcium-Ion
dc0f303bb7 Merge pull request #1184 from QuantumNous/refactor/message
fix: message 转 any 后,ImageUrl判断 panic
2025-06-09 15:51:53 +08:00
Xyfacai
c95fb55c51 fix: message 转 any 后,ImageUrl判断 panic 2025-06-09 11:27:24 +08:00
CaIon
865377449e refactor(dto): change function and encoding fields to use json.RawMessage for improved flexibility 2025-06-08 16:28:47 +08:00
Xyfacai
b778cd2b23 refactor: message content 改成 any
refactor: message content 改成 any
2025-06-07 23:47:22 +08:00
neotf
e77555a04f Merge branch 'main' into feat-04 2025-06-05 20:35:47 +08:00
neotf
3665ad672e feat: support claude cache and thinking for upstream [OpenRouter] (#983)
* feat: support claude cache for upstream [OpenRouter]

* feat: support claude thinking for upstream [OpenRouter]

* feat: reasoning is common params for OpenRouter
2025-06-05 17:35:48 +08:00
CaIon
611d77e1a9 feat: add ToMap method and enhance OpenAI request handling 2025-06-01 01:10:10 +08:00
neotf
66778efcc5 feat: enhance token usage details for upstream OpenRouter 2025-05-29 00:55:57 +08:00
CaIon
e01b517843 fix: Change ParallelTooCalls from bool to *bool in GeneralOpenAIRequest for optional handling 2025-05-28 21:12:55 +08:00
IcedTangerine
e3d7b31a49 Update openai_request.go 2025-05-28 14:25:24 +08:00
wang.rong
76824a0337 chat/completion透传parallel_tool_calls参数 2025-05-27 09:32:20 +08:00
creamlike1024
30d5a11f46 fix: search-preview model web search billing 2025-05-26 18:53:41 +08:00
Calcium-Ion
48af027903 Merge pull request #1020 from QuantumNous/v1responses
feat: support /v1/responses API
2025-05-04 17:13:39 +08:00
CaIon
e097d5a538 feat: add video URL support in MediaContent and update token counting logic 2025-05-03 21:12:07 +08:00
creamlike1024
425feb88d8 feat: support /v1/responses API 2025-05-02 13:59:46 +08:00
CaIon
b64480b750 fix: gemini thinking tokens count #1014 2025-04-29 16:21:54 +08:00
CaIon
1eebdc4773 refactor: remove reasoning field from GeneralOpenAIRequest struct 2025-04-17 17:11:42 +08:00
CaIon
9b6c898675 feat: add reasoning field to GeneralOpenAIReques 2025-04-17 17:09:46 +08:00
CaIon
4b3e30e669 feat: 完善openai转claude支持 2025-04-11 18:28:50 +08:00
CaIon
cca9c0479f feat: enhance file handling and logging in the application 2025-04-11 16:23:54 +08:00
1808837298@qq.com
dd393cd0d9 feat: support dify upload image file 2025-03-15 19:10:12 +08:00
Sh1n3zZ
b95142bbac fix: adapting return format for openrouter think content (#793) 2025-03-06 19:16:26 +08:00
1808837298@qq.com
13ab0f8e4f fix: gemini&claude tool call format #795 #766 2025-02-26 23:56:10 +08:00
Calcium-Ion
dc36fdedc2 Merge pull request #781 from zeyugao/main
feat: Pass extra_body in OpenAI request to the backend
2025-02-24 16:29:48 +08:00
1808837298@qq.com
7ff4cebdbe feat: Enhance token counting and content parsing for messages 2025-02-24 14:18:15 +08:00
Elsa
af00f7b311 Pass extra_body to the backend 2025-02-24 10:52:55 +08:00
1808837298@qq.com
88a2fec190 fix: mistral 2025-02-22 16:29:48 +08:00
1808837298@qq.com
cc5066c510 refactor: Improve message content parsing with robust type handling 2025-02-21 18:27:43 +08:00
1808837298@qq.com
b9b69b01e5 refactor: Improve message content handling and quota error responses 2025-02-21 18:18:21 +08:00
1808837298@qq.com
971aea09ee feat: Improve image handling for Ollama channels 2025-02-19 20:45:42 +08:00
1808837298@qq.com
3da1344897 feat: Add user notification settings with quota warning and multiple notification methods
- Implement user notification settings with email and webhook options
- Add new user settings for quota warning threshold and notification preferences
- Create backend API and database support for user notification configuration
- Enhance frontend personal settings with notification configuration UI
- Support custom notification email and webhook URL
- Add service layer for sending user notifications
2025-02-18 14:54:21 +08:00
Calcium-Ion
78f19d4690 Merge pull request #735 from jyc001/main
feat:Add Supoorts to FIM
2025-02-17 14:37:06 +07:00
1808837298@qq.com
1f527ffc50 feat: enhance OpenAI request and response DTOs
- Add `Prefix` and `ReasoningContent` fields to Message struct
- Add getter and setter methods for `Prefix`
- Make `ToolCall.ID` field optional (fix #749)
2025-02-11 19:54:54 +08:00
e.
1eb72f2f22 fix: correct JSON tags for Prompt and Suffix in GeneralOpenAIRequest 2025-02-08 00:36:42 +08:00
e.
8082905184 feat: add Suffix to GeneralOpenAIRequest in order to support FIM 2025-02-08 00:25:08 +08:00
Butui Hu
eda7ef50e0 Fix temperature not being set to 0 due to json omitempty
The issue was caused by the `omitempty` tag in the Go struct, which prevented the `temperature` field from being included in the JSON output when it was set to 0.

Signed-off-by: Butui Hu <hot123tea123@gmail.com>
2025-01-21 12:54:09 +08:00
CalciumIon
c4e256e69b refactor: Update Message methods to use pointer receivers
- Refactored ParseToolCalls, SetToolCalls, IsStringContent, and ParseContent methods in the Message struct to use pointer receivers, improving efficiency and consistency in handling mutable state.
- Enhanced code readability and maintainability by ensuring all relevant methods operate on the pointer receiver, aligning with Go best practices.
2024-12-22 16:30:18 +08:00